Case Studies
Real-world results from running Nerviq across different stacks, platforms, and team configurations.
Typical Next.js SaaS
nerviq setup delivered +44 points on a greenfield Next.js repo in one pass.
Stripe Integration App
Payment-adjacent repos benefit sharply from explicit trust and secret-handling checks.
Mobile App
Mobile stacks need explicit build/run documentation for agent reliability.
Turborepo Monorepo
Monorepos score lower without root-level agent map and package boundaries.
Node CLI Package
CLI projects gain from documented release and test entrypoints.
FastAPI Backend
Python services start higher (~50) thanks to opinionated tooling and layouts.
Django Web App
Django conventions help scores but agent instructions often omit deployment context.
Go Microservice
Go repos benefit from explicit module boundaries in instructions.
Rust Library
Rust projects score well on hygiene; tooling docs close the last mile.
LangChain / RAG Project
ML repos need explicit data-handling and evaluation instructions for safe agents.
Claudex Research Engine (live)
Highly configured research repo; intentional gaps in container/IaC signals.
Nerviq CLI — Claude audit (live)
Self-audit: nerviq meets its own Claude Code bar with zero critical issues.
Nerviq CLI — Codex uplift (live)
+49 points after setup proves Codex path parity with deliberate AGENTS.md work.
Cross-platform self-check (Codex)
82 Codex vs 83 Claude — near-identical alignment when AGENTS.md anchors intent.
Claude + Codex on one repo
One critical Codex CI auth gap; otherwise strong two-platform alignment.
Claude + Cursor + Copilot
Harmony moved 42→84 after introducing AGENTS.md as shared anchor.
All eight platforms
Eight platforms is viable; security drift is the dominant risk vector.
10-person TypeScript monorepo
+42 harmony points in six weeks; ~65 engineer-hours invested.
200-contributor OSS library
Contributor heterogeneity makes AGENTS.md non-optional.
Two-founder MVP (8 weeks)
~3 hour setup investment → +40–45 points within two weeks.
PCI + SOC 2 payments platform
Compliance forcing functions produced the highest harmony in the corpus.
Terraform + Kubernetes platform
Pre-tool-use hooks and blast-radius docs matter more than generic linting.
Cursor → Claude expansion
.cursorrules silently ignored in Agent mode until nerviq surfaced it.
90-day controlled synergy study
High harmony (80+) multiplies value; low harmony barely beats single-platform.
24-study cross-cutting synthesis
AGENTS.md appears in 18/24 studies as the primary harmony driver.